Learning semantic structures from in-domain documents
Name
725620956-MIT.pdf
Description
Full printable version
Size
12.63 MB
Format
Adobe PDF
Checksum (MD5)
c93384f495e006f2b22c7596267998d5
Author(s)
Chen, Harr
Advisor(s)
Regina Barzilay and David R. Karger.
Date Issued
2011
Publisher
Massachusetts Institute of Technology
Abstract
Semantic analysis is a core area of natural language understanding that has typically focused on predicting domain-independent representations. However, such representations are unable to fully realize the rich diversity of technical content prevalent in a variety of specialized domains. Taking the standard supervised approach to domainspecific semantic analysis requires expensive annotation effort for each new domain of interest. In this thesis, we study how multiple granularities of semantic analysis can be learned from unlabeled documents within the same domain. By exploiting in-domain regularities in the expression of text at various layers of linguistic phenomena, including lexicography, syntax, and discourse, the statistical approaches we propose induce multiple kinds of structure: relations at the phrase and sentence level, content models at the paragraph and section level, and semantic properties at the document level. Each of our models is formulated in a hierarchical Bayesian framework with the target structure captured as latent variables, allowing them to seamlessly incorporate linguistically-motivated prior and posterior constraints, as well as multiple kinds of observations. Our empirical results demonstrate that the proposed approaches can successfully extract hidden semantic structure over a variety of domains, outperforming multiple competitive baselines.
Description
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2011.
Cataloged from PDF version of thesis.
Includes bibliographical references (p. 175-184).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
M.I.T. theses are protected by
copyright. They may be viewed from this source for any purpose, but
reproduction or distribution in any format is prohibited without written
permission. See provided URL for inquiries about permission.
copyright. They may be viewed from this source for any purpose, but
reproduction or distribution in any format is prohibited without written
permission. See provided URL for inquiries about permission.
Persistent DSpace Link
